Sign Language Recognition and Interpretation System

Abstract

Sign language is a visual language that individuals with speech and hearing difficulties use to communicate in their daily conversations. Through its original grammar, it is totallyan optical communication language, as opposed to vocal languages. This study report proposed an effective strategy to accomplishing the translation of 24 static sign language alphabets and numerals of American Sign Language into humanoid. Researchers are now focusing their efforts on building commercially viable Sign Language Recognition systems. Researchers use a range of techniques to perform their research. It all starts with the methods of data acquisition. The data collection method varies depending on the cost of a suitable device, however for the Sign Language Recognition System to be commercialized, a low-cost strategy is required. The methods used by researchers to develop Sign Language Recognition varied as well. Each approach has its own advantages over others, and researchers are continually experimenting with various methods to produce their own Sign Language Recognition. Each approach has its own set of limitations when compared to others. The purpose of this study is to examine several ways to sign language recognitionand choose the optimal method. Keywords — Feature Extraction and Representation, Artificial Neural Networks, Convolution Neural Network, TensorFlow, Keras, OpenCV.